Frank a08be1641f frank-default-large: full native 262144 context per slot (524288 total) ...

llama.cpp splits -c across -np slots; to give each of the 2 slots the full
262144 native context, set CTX_SIZE=524288. KV ~32 GiB; fits the 96 GiB
unified pool. Update env default, serve-script fallback, and the deployment
doc line.

2026-08-18 08:01:17 -07:00

..

Pipeline Parallelism

fleet redo 2026-08-17: retire PP+NPU, new topology

2026-08-17 15:23:46 -07:00

ciru-activefpx-promptforge.md

docs: note 128K context and thinking on for frank-default-small

2026-08-17 23:12:32 -07:00

Dankclaw Improvements.md

PP kit + Strix research: Qwen3.8-27B RPC split (Dankclaw head / Dankserver worker)

2026-08-16 05:40:27 -07:00

Dankclaw System Specs.md

docs: reflect CIRU runtime on Dankclaw in specs and deployment pages

2026-08-17 21:14:16 -07:00

Dankserver System Specs.md

docs: measured PP link math (H=5120 verified, 20.5 MB/ubatch wire), NIC inventory

2026-08-17 05:06:41 -07:00

dankserver-vram-growth.md

fleet redo 2026-08-17: retire PP+NPU, new topology

2026-08-17 15:23:46 -07:00

deployment.md

frank-default-large: full native 262144 context per slot (524288 total)

2026-08-18 08:01:17 -07:00

DFlash DSpark Speculative Decoding.md

docs: boot policy (only PP units enabled), deploy.sh dankserver hazard, stale-claim cleanup

2026-08-17 03:30:00 -07:00

FastFlowLM NPU Inference.md

docs: mark retired FastFlowLM/NPU pages with the port/name handoff; tighten Dankclaw system specs runtime row

2026-08-17 18:10:57 -07:00

frank-default-large-benchmark.md

fleet redo 2026-08-17: retire PP+NPU, new topology

2026-08-17 15:23:46 -07:00

frank-default-small-benchmark.md

docs: record dual-f16 KV refit on frank-default-small (2026-08-14)

2026-08-14 12:59:10 -07:00

frank-redo-2026-08-17.md

docs: note prefix caching enabled on frank-default-small (opt-in for hybrid; ~4x TTFT on repeated prefix)

2026-08-17 18:45:49 -07:00

Hybrid CPU GPU Processing Dankserver.md

docs: polish pass — fix stale names, duplicates, branding, and README

2026-08-10 21:12:23 -07:00

index.md

Docs: reflect the 2026-08-18 second swap (rename + Qwen3.6 restore)

2026-08-18 01:29:21 -07:00

ling-3.0-flash-trial.md

docs: boot policy (only PP units enabled), deploy.sh dankserver hazard, stale-claim cleanup

2026-08-17 03:30:00 -07:00

ling-3.0-flash-vllm-plan.md

docs: boot policy (only PP units enabled), deploy.sh dankserver hazard, stale-claim cleanup

2026-08-17 03:30:00 -07:00

Quantization by Hardware Architecture.md

docs: reflect Ling-3 vLLM (frank-default-large) on Dankclaw

2026-08-10 23:37:27 -07:00

qwen3.8-spec-matrix.md

fleet redo 2026-08-17: retire PP+NPU, new topology

2026-08-17 15:23:46 -07:00

qwen3.8-strix-optimizations.md

PP kit + Strix research: Qwen3.8-27B RPC split (Dankclaw head / Dankserver worker)

2026-08-16 05:40:27 -07:00

RAM CPU Offloading in VLLM.md

docs: polish pass — fix stale names, duplicates, branding, and README

2026-08-10 21:12:23 -07:00

Running Qwen3.6 27B FP8 on Dankclaw.md

docs: correct Dankclaw RAM figure (64 GiB, 61 GiB visible)

2026-08-17 20:34:51 -07:00

Running Qwen3.6 35B A3B FP8 on Dankserver.md

docs: boot policy (only PP units enabled), deploy.sh dankserver hazard, stale-claim cleanup

2026-08-17 03:30:00 -07:00

Shared Memory Architecture Dankclaw.md

docs: correct Dankclaw RAM figure (64 GiB, 61 GiB visible)

2026-08-17 20:34:51 -07:00

VLLM Index.md

docs: polish pass — fix stale names, duplicates, branding, and README

2026-08-10 21:12:23 -07:00

VLLM Overview.md

docs: polish pass — fix stale names, duplicates, branding, and README

2026-08-10 21:12:23 -07:00

vllm_research_findings.md

feat: initial vLLM Qwen3.6-35B-A3B-FP8 serve script with DFlash drafting on dankserver

2026-08-07 18:28:38 -07:00